conftrace_

attention optimization

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

kv cache (4) large language model (3) inference efficiency (3) key-value cache (2) kv cache compression (2) computational efficiency (2) attention mechanism (2) attention computation (1) context window extension (1) selective compression (1)

Papers

HShare: Fast LLM Decoding by Hierarchical Key-Value Sharing ICLR 2025 Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 Eigen Attention: Attention in Low-Rank Space for KV Cache Compression EMNLP 2024 SCA: Selective Compression Attention for Efficiently Extending the Context Window of Large Language Models EMNLP 2024 H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models NeurIPS 2023